| User | ju83 |
| Upload Date | December 30 2024 09:20 PM |
| Views | 13 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A12 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.2 |
| Model | iPhone XS |
| Model ID | iPhone11,2 |
| Motherboard | D321AP |
| CPU Information | |
|---|---|
| Name | Apple A12 Bionic |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 2.49 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 3.69 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
229
42.6 IPS |
|
|
Image Classification (HP)
|
100% |
261
48.6 IPS |
|
|
Image Classification (Q)
|
96% |
136
25.4 IPS |
|
|
Image Segmentation (SP)
|
100% |
217
3.51 IPS |
|
|
Image Segmentation (HP)
|
100% |
249
4.03 IPS |
|
|
Image Segmentation (Q)
|
99% |
175
2.84 IPS |
|
|
Pose Estimation (SP)
|
100% |
1612
1.88 IPS |
|
|
Pose Estimation (HP)
|
100% |
2218
2.59 IPS |
|
|
Pose Estimation (Q)
|
96% |
688
0.81 IPS |
|
|
Object Detection (SP)
|
100% |
516
40.9 IPS |
|
|
Object Detection (HP)
|
100% |
548
43.4 IPS |
|
|
Object Detection (Q)
|
92% |
156
12.5 IPS |
|
|
Face Detection (SP)
|
100% |
1948
23.1 IPS |
|
|
Face Detection (HP)
|
100% |
2250
26.7 IPS |
|
|
Face Detection (Q)
|
100% |
246
2.92 IPS |
|
|
Depth Estimation (SP)
|
100% |
1682
13.0 IPS |
|
|
Depth Estimation (HP)
|
99% |
1669
12.9 IPS |
|
|
Depth Estimation (Q)
|
86% |
416
3.25 IPS |
|
|
Style Transfer (SP)
|
100% |
4067
5.23 IPS |
|
|
Style Transfer (HP)
|
100% |
3383
4.35 IPS |
|
|
Style Transfer (Q)
|
96% |
1499
1.93 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
779
28.7 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
886
32.7 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
270
9.96 IPS |
|
|
Text Classification (SP)
|
100% |
149
199.2 IPS |
|
|
Text Classification (HP)
|
100% |
197
263.5 IPS |
|
|
Text Classification (Q)
|
93% |
201
270.3 IPS |
|
|
Machine Translation (SP)
|
100% |
169
2.92 IPS |
|
|
Machine Translation (HP)
|
100% |
153
2.64 IPS |
|
|
Machine Translation (Q)
|
98% |
154
2.66 IPS |